公开(公告)号：US20250046333A1

公开(公告)日：2025-02-06

申请号：US18727279

申请日：2022-12-16

Applicant: SRI International

Inventor： Martin Graciarena ,  Aaron Dennis Lawson ,  MD Hafizur Rahman

IPC: G10L25/51 ,  G10L25/30

Abstract: In general, the disclosure describes a computing system to automatically identify and classify audio input, including non-speech audio signals. The computing system may also add new classes based on only a limited number of examples of the new classes, to identify classes of sounds for which the system had not been trained.

公开(公告)号：US20250041315A1

公开(公告)日：2025-02-06

申请号：US18718737

申请日：2022-12-13

Applicant: The USA, as Represented by the Secretary, Department of Health and Human Services ,  SRI International

Inventor： Min Lee ,  Diana Blithe ,  Jia-Hwa Fang ,  Eduardo Ruiz ,  Ken Chen

IPC: A61K31/565 ,  A61K9/16

Abstract: Disclosed herein are formulation embodiments comprising levonorgestrel butanoate (“LNGB”) particles having particle sizes that facilitate administering a higher concentration of LNGB at lower volumes. The disclosed formulation embodiments exhibit long-lasting contraceptive effects and can be administered subcutaneously, which lends to their utility in acting as self-administrable contraceptive formulations that do not result in side effects associated with other contraceptive agents.

公开(公告)号：US20250040265A1

公开(公告)日：2025-01-30

申请号：US18717984

申请日：2022-11-17

Applicant: SRI International

Inventor： John McCarten ,  Namwoong Paik

IPC: H01L27/146 ,  H01L31/101

Abstract: In general, the disclosure describes sensor including an intermediate band layer including a plurality of dopant particles, wherein the intermediate band layer is configured to absorb a portion of incident electromagnetic radiation comprising a first range of wavelengths greater than 1100 nm and form optically induced minority carriers. The sensor also includes a photo-sensitive silicon substrate configured to detect the electromagnetic radiation comprising a second range of wavelengths less than or equal to 1100 nm.

公开(公告)号：US20250029601A1

公开(公告)日：2025-01-23

申请号：US18769197

申请日：2024-07-10

Applicant: SRI International

Inventor： MD Hafizur Rahman ,  Mitchell Leigh McLaren ,  Aaron Dennis Lawson

IPC: G10L15/16 ,  G10L15/32

Abstract: In general, the disclosure describes techniques for detecting synthetic speech of a speaker. In an example, a machine learning system may be configured to generate, using a deep learning model trained to distinguish between synthetic speech and authentic speech, reference embeddings for the speaker that characterize a first set of acoustic features and a first set of phonetic features associated with the speaker. The machine learning system may further be configured to generate, using the deep learning model, a test embedding for an audio clip that characterizes a second set of acoustic features and a second set of phonetic features associated with the audio clip. The machine learning system may further be configured to compute a score based on the test embedding and the reference embeddings. The machine learning system may further be configured to output, based on the score, an indication of whether the audio clip includes synthetic speech.

公开(公告)号：US20250013873A1

公开(公告)日：2025-01-09

申请号：US18766378

申请日：2024-07-08

Applicant: SRI International

Inventor： Ajay DIVAKARAN ,  Karan SIKKA ,  Michael COGSWELL ,  Yunye GONG ,  Yangyi CHEN

IPC: G06N3/098 ,  G06F30/27 ,  G06F40/40 ,  G06N3/0475

Abstract: A method, apparatus, and system for training a language model for enhanced consistency include selecting at least a portion of the content data of the language model, generating reasoning statements in the form of natural language relevant to the selected portion of the content data, and training the language model using the generated reasoning statements such that a logical inference of the trained language model in response to a prompt directed to the selected portion of the content data is increased as compared with the logical inference of the language model in response to the same or similar prompt before the training of the language model to enhance the consistency of the language model with respect to the selected portion of the content data. The trained language model can be used to generate a logical inference having enhanced consistency for at least a portion of content data.

公开(公告)号：US20240430685A1

公开(公告)日：2024-12-26

申请号：US18748496

申请日：2024-06-20

Applicant: SRI International

Inventor： Ashish Gehani ,  Vinod Trivandrum Yegneswaran ,  Phillip Andrew Porras

IPC: H04W12/122

Abstract: An example method for identifying one or more potential malicious activities in a software-defined open radio access network includes detecting, by a trusted monitoring device, a communication flow from a sender component to a receiver component via an intermediate component. The method also includes, in response to the detecting of the communication flow, generating, by the trusted monitoring device and utilizing an intermediate identifier associated with the intermediate component, a flow record based on one or more parameters associated with the communication flow. The method further includes providing, by the trusted monitoring device and based on the flow record, an indication of the one or more potential malicious activities in the software-defined open radio access network.

公开(公告)号：US20240403728A1

公开(公告)日：2024-12-05

申请号：US18614388

申请日：2024-03-22

Applicant: SRI International

Inventor： Yunye Gong ,  Yi Yao ,  Xiao Lin ,  Ajay Divakaran

IPC: G06N20/20 ,  G06N7/01

Abstract: In general, techniques are described that address the limitations of existing conformal prediction methods for cascaded models. In an example, a method includes receiving a first validation data set for validating performance of an upstream model of the two or more cascaded models and receiving a second validation data set for validating performance of a downstream model of the two or more cascaded models wherein the second validation data set is different than the first validation set; estimating system-level errors caused by predictions of the upstream model based on the first validation data set; estimating system-level errors caused by predictions of the downstream model based on the second validation data set; and generating a prediction confidence interval that indicates a confidence for the system based on the system-level errors caused by predictions of the upstream model and based on the system-level errors caused by predictions of the downstream model.

公开(公告)号：US20240403649A1

公开(公告)日：2024-12-05

申请号：US18520800

申请日：2023-11-28

Applicant: SRI International

Inventor： Han-Pang Chiu ,  Yi Yao ,  Zachary Seymour ,  Alex Krasner ,  Bradley J. Clymer ,  Michael A. Cogswell ,  Cecile Eliane Jeannine Mackay ,  Alex C. Tozzo ,  Tixiao Shan ,  Philip Miller ,  Chuanyong Gan ,  Glenn A. Murray ,  Richard Louis Ferranti ,  Uma Rajendran ,  Supun Samarasekera ,  Rakesh Kumar ,  James Smith

IPC: G06N3/0895

Abstract: In an example, a system includes processing circuitry in communication with storage media. The processing circuitry is configured to execute a machine learning system including at least a first module, a second module and a third module. The machine learning system is configured to train one or more machine learning models. The first module is configured to generate augmented input data based on the streaming input data. The second module includes a machine learning model configured to perform a specific task based at least in part on the augmented input data. The third module configured to adapt a network architecture of the one or more machine learning models based on changes in the streaming input data.

公开(公告)号：US12118773B2

公开(公告)日：2024-10-15

申请号：US17129541

申请日：2020-12-21

Applicant: SRI International

Inventor： Girish Acharya ,  Louise Yarnall ,  Anirban Roy ,  Michael Wessel ,  Yi Yao ,  John J. Byrnes ,  Dayne Freitag ,  Zachary Weiler ,  Paul Kalmar

IPC: G06V10/82 ,  G06F18/22 ,  G06N20/00 ,  G06V20/20 ,  G06V20/40 ,  G06V30/19 ,  G06V30/262 ,  G06V40/10 ,  G06V40/20 ,  G09B5/06 ,  G09B19/00 ,  G10L15/18 ,  G10L25/57

CPC classification number: G06V10/82 ,  G06F18/22 ,  G06N20/00 ,  G06V20/20 ,  G06V20/41 ,  G06V30/19173 ,  G06V30/274 ,  G06V40/10 ,  G06V40/113 ,  G06V40/28 ,  G09B5/065 ,  G09B19/003 ,  G10L15/1815 ,  G10L25/57

Abstract: This disclosure describes machine learning techniques for capturing human knowledge for performing a task. In one example, a video device obtains video data of a first user performing the task and one or more sensors generate sensor data during performance of the task. An audio device obtains audio data describing performance of the task. A computation engine applies a machine learning system to correlate the video data to the audio data and sensor data to identify portions of the video, sensor, and audio data that depict a same step of a plurality of steps for performing the task. The machine learning system further processes the correlated data to update a domain model defining performance of the task. A training unit applies the domain model to generate training information for performing the task. An output device outputs the training information for use in training a second user to perform the task.

公开(公告)号：US20240338599A1

公开(公告)日：2024-10-10

申请号：US18619916

申请日：2024-03-28

Applicant: SRI International

Inventor： Karan SIKKA ,  Michael COGSWELL ,  Pritish SAHU ,  Meng YE ,  Abrar RAHMAN ,  Rohit SRIDHAR ,  Ajay DIVAKARAN

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: A method, apparatus and system for adapting a language model for understanding domain-specific multimodal content include acquiring domain-specific multimodal content for at least one content domain and applying question/answer pairs to the acquired, domain-specific multimodal content for the at least one content domain to train the language model to learn tasks associated with the domain-specific multimodal content for the at least one domain. As such, the trained language model can be implemented to answer questions directed to the domain-specific multimodal content for the at least one domain.